Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the word "over" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     overview
    -0.22
    overview
    -0.21
     Overview
    -0.21
    Overview
    -0.20
     overloaded
    -0.19
    sonian
    -0.18
     Oversight
    -0.18
    overwrite
    -0.17
     overlap
    -0.17
     override
    -0.17
    POSITIVE LOGITS
    tones
    0.29
    alls
    0.29
    lord
    0.28
    lying
    0.28
    tures
    0.27
    heard
    0.26
    hang
    0.26
    flows
    0.25
    ture
    0.25
    comes
    0.25
    Act Density 0.165%

    No Known Activations